© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130288
    Prev
    Next
    INDEX
    Explanations

    Balance/imbalance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivre
    -0.28
    ibili
    -0.27
    èµłéĢģ
    -0.27
    è´Ī
    -0.26
     targeting
    -0.26
    äºĴè¡¥
    -0.25
    _HT
    -0.24
    ivities
    -0.24
     fluores
    -0.24
    hek
    -0.24
    POSITIVE LOGITS
    ä¸Ģç»ı
    0.32
     quad
    0.26
     sürü
    0.25
     linkage
    0.25
     Term
    0.24
    åľ¨ä¸Ģèµ·
    0.24
     mult
    0.24
    Fa
    0.24
     entire
    0.23
    æķ´ä½ĵ
    0.23
    Activations Density 4.294%

    No Known Activations